Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    operations on both sides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിന്ന
    0.40
    leyball
    0.38
    可通过
    0.38
    ⅳ
    0.37
    ClrType
    0.36
     هیچ
    0.36
     कोशिश
    0.36
     Militar
    0.36
     ajuta
    0.36
    तौर
    0.36
    POSITIVE LOGITS
     resulting
    0.62
     yields
    0.58
     ergibt
    0.57
     resulted
    0.56
     gives
    0.52
     creates
    0.52
     resulta
    0.52
     yielding
    0.50
     hasilnya
    0.50
     formando
    0.50
    Act Density 0.064%

    No Known Activations